NWPU_VHR-10

displayName: NWPU VHR-10
license:
- MIT
publishDate: "2019"
publishUrl: https://github.com/chaozhong2010/VHR-10_dataset_coco
publisher:
- Northwestern Polytechnical University
tags:
- Airplane
- Ship

---
# 数据集介绍
## 简介
NWPU VHR-10数据集是具有挑战性的十类地理空间对象检测数据集。该数据集总共包含800幅VHR光学遥感图像，其中715幅彩色图像是从谷歌地球获得的，空间分辨率从0.5到2米，从具有0.08 m的空间分辨率的Vaihingen数据获取85幅经锐化的彩色红外图像。该数据集被分成两组: a) 在图像中包含至少一个目标的正图像集包含650图像。b) 负图像集包含150图像，并且它不包含任何目标。由此，正面图像集、757飞机、302船只、655储罐、390棒球钻石、524网球场、159篮球场、163地面田径场、224港口、124桥梁和477车辆被手动注释为边界框和用于地面真相的实例面具。

## Download dataset
:modelscope-code[]{type="git"}

displayName: NWPU VHR-10
license:
- MIT
publishDate: "2019"
publishUrl: https://github.com/chaozhong2010/VHR-10_dataset_coco
publisher:
- Northwestern Polytechnical University
tags:
- Airplane
- Ship

---

# Dataset Introduction
## Introduction
The NWPU VHR-10 dataset is a challenging ten-class geospatial object detection dataset. The dataset contains a total of 800 VHR optical remote sensing images, among which 715 color images were obtained from Google Earth with spatial resolutions ranging from 0.5 to 2 meters, and 85 sharpened color infrared images were acquired from the Vaihingen dataset which has a spatial resolution of 0.08 m. The dataset is split into two subsets: a) The positive image set, which contains at least one target object per image, comprises 650 images. b) The negative image set, which contains no target objects whatsoever, consists of 150 images. In total, 757 airplanes, 302 ships, 655 storage tanks, 390 baseball diamonds, 524 tennis courts, 159 basketball courts, 163 ground track fields, 224 ports, 124 bridges and 477 vehicles within the positive image set were manually annotated with bounding boxes and instance masks for ground truth.

## Download Dataset
:modelscope-code[]{type="git"}

搜集汇总

背景与挑战

背景概述

NWPU VHR-10是一个包含10类地理空间目标检测的挑战性数据集，包含800张高分辨率遥感图像，分为正负样本集，其中正样本集包含650张图像并标注了757架飞机、302艘船等10类目标的边界框和实例掩码。图像来源包括Google Earth和Vaihingen数据集，空间分辨率从0.5米到0.08米不等。